File size: 1,896 Bytes
344269b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 |
import tensorflow as tf
from transformers import BertTokenizer
from transformers import TFBertForSequenceClassification
from Sastrawi.Stemmer.StemmerFactory import StemmerFactory # Import Sastrawi
import streamlit as st
# Fungsi untuk memuat model BERT dan tokenizer
PRE_TRAINED_MODEL = 'indobenchmark/indobert-base-p2'
bert_tokenizer = BertTokenizer.from_pretrained(PRE_TRAINED_MODEL)
bert_model = TFBertForSequenceClassification.from_pretrained(PRE_TRAINED_MODEL, num_labels=2)
bert_model.load_weights('model.h5')
# Inisialisasi stemmer dari Sastrawi
stemmer = StemmerFactory().create_stemmer() # Membuat stemmer Sastrawi
def preprocess_text(text):
# Menggunakan Sastrawi untuk stemming
stemmed_text = stemmer.stem(text.lower())
return stemmed_text
def predict_sentiment(text):
preprocessed_text = preprocess_text(text) # Pra-pemrosesan teks dengan Sastrawi
input_ids = tf.constant(bert_tokenizer.encode(preprocessed_text, add_special_tokens=True))[None, :]
logits = bert_model(input_ids)[0]
probabilities = tf.nn.softmax(logits, axis=1)
sentiment = tf.argmax(probabilities, axis=1)
return sentiment.numpy()[0], probabilities.numpy()[0]
# Judul aplikasi
st.title('Prediksi Sentimen menggunakan BERT')
# Input teks
text = st.text_area('Masukkan teks', '')
# Tombol untuk memprediksi sentimen
if st.button('Prediksi'):
if text.strip() == '':
st.warning('Masukkan teks terlebih dahulu.')
else:
sentiment, probabilities = predict_sentiment(text)
# Menghitung persentase probabilitas sentimen positif
positive_probability = probabilities[1] * 100
negative_probability = probabilities[0] * 100
st.write(f'HASIL PREDIKSI')
if sentiment == 0:
st.write(f'Negatif ({negative_probability:.2f}%)')
else:
st.write(f'Positif ({positive_probability:.2f}%)') |